§
    ‚Štj°�  ã                   óv  — d dl mZ d dlmZ d dlZd dlmc mZ d dlmZ ddl	m
Z ddlmZ ddlmZmZ dd	lmZ dd
lmZmZmZmZ ddlmZmZ ddlmZ ddlmZ ddlm Z m!Z! ddl"m#Z#m$Z$ ddl%m&Z&m'Z' ddl(m)Z) ddl*m+Z+m,Z, ddl-m.Z.m/Z/m0Z0 ddl1m2Z2m3Z3 ddl4m5Z5  G d„ dej6        ¦  «        Z7 ed¦  «         G d„ dej6        ¦  «        ¦   «         Z8d„ Z9 ed¦  «        dDd„¦   «         Z:dej;        d e<d!ej;        fd"„Z=	 dEd$ej6        d%ej;        d&ej;        d'ej;        d(ej;        dz  d)e>d*e>d+e)e.         fd,„Z? ee:¦  «         G d-„ d.ej6        ¦  «        ¦   «         Z@e G d/„ d0ej6        ¦  «        ¦   «         ZA G d1„ d2ej6        ¦  «        ZB G d3„ d4ej6        ¦  «        ZC G d5„ d6ej6        ¦  «        ZD G d7„ d8e¦  «        ZEe+ G d9„ d:e'¦  «        ¦   «         ZFe+ G d;„ d<eF¦  «        ¦   «         ZG	 	 	 dFd>ej;        eHej;                 z  dz  d?e<dz  d(ej;        dz  d!ej;        e<z  fd@„ZIe+ G dA„ dBeFe¦  «        ¦   «         ZJg dC¢ZKdS )Gé    )ÚCallable)ÚOptionalN)Únné   )Úinitialization)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_experts_implementationÚuse_kernel_forward_from_hubÚuse_kernel_func_from_hubÚuse_kernelized_func)Úcreate_causal_maskÚ!create_sliding_window_causal_mask)ÚFlashAttentionKwargs)ÚGradientCheckpointingLayer)ÚMoeCausalLMOutputWithPastÚMoeModelOutputWithPast)ÚROPE_INIT_FUNCTIONSÚdynamic_rope_update)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)Úauto_docstringÚcan_return_tuple)ÚTransformersKwargsÚmaybe_autocastÚmerge_with_config_defaults)ÚOutputRecorderÚcapture_outputsé   )ÚMellumConfigc                   óà   ‡ — e Zd ZU ej        ed<   defˆ fd„Ze	 	 	 	 ddedz  de	d         de
dz  dedz  d	ed
ef         f
d„¦   «         Z ej        ¦   «         edd„¦   «         ¦   «         Zˆ xZS )ÚMellumRotaryEmbeddingÚinv_freqÚconfigc                 ó€  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        t          t          |j        ¦  «        ¦  «        | _        i | _	        | j        D ]È}| j        j
        |         }|€Œ|d         | j	        |<   | j        }| j	        |         dk    rt          | j	        |                  } || j        |¬¦  «        \  }}|                      |› d�|d¬¦  «         |                      |› d�|                     ¦   «         d¬¦  «         t          | |› d�|¦  «         ŒÉd S )	NÚ	rope_typeÚdefault©Ú
layer_typeÚ	_inv_freqF)Ú
persistentÚ_original_inv_freqÚ_attention_scaling)ÚsuperÚ__init__Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr'   ÚlistÚsetÚlayer_typesr)   Úrope_parametersÚcompute_default_rope_parametersr   Úregister_bufferÚcloneÚsetattr)Úselfr'   r,   Úrope_paramsÚrope_init_fnÚcurr_inv_freqÚcurr_attention_scalingÚ	__class__s          €úh/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/mellum/modeling_mellum.pyr2   zMellumRotaryEmbedding.__init__6   s^  ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*Ô$BˆÔ!ØˆŒÝ¥ FÔ$6Ñ 7Ô 7Ñ8Ô8ˆÔØˆŒØÔ*ð 	Uð 	UˆJØœ+Ô5°jÔAˆKØÐ"Øà)4°[Ô)AˆDŒN˜:Ñ&Ø%)Ô%IˆLØŒ~˜jÔ)¨YÒ6Ð6Ý2°4´>À*Ô3MÔN�Ø4@°LÀÄÐYcÐ4dÑ4dÔ4dÑ1ˆMÐ1Ø× Ò  JÐ!9Ð!9Ð!9¸=ÐUZÐ Ñ[Ô[Ð[Ø× Ò  JÐ!BÐ!BÐ!BÀM×DWÒDWÑDYÔDYÐfkÐ ÑlÔlÐlÝ�D˜ZÐ;Ð;Ð;Ð=SÑTÔTÐTÐTð	Uð 	Uó    NÚdeviceztorch.deviceÚseq_lenr,   Úreturnztorch.Tensorc                 ón  — | j         |         d         }| j         |                              dd¦  «        }t          | dd¦  «        p| j        | j        z  }t          ||z  ¦  «        }d}d|t          j        d|dt          j        ¬¦  «         	                    |t          j
        ¬	¦  «        |z  z  z  }	|	|fS )
a{  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
            layer_type (`str`, *optional*):
                The current layer type if the model has different RoPE parameters per type.
                Should not be used unless `config.layer_types is not None`
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚpartial_rotary_factorg      ð?Úhead_dimNr   é   ©Údtype)rF   rO   )r9   ÚgetÚgetattrÚhidden_sizeÚnum_attention_headsÚintÚtorchÚarangeÚint64ÚtoÚfloat)
r'   rF   rG   r,   ÚbaserK   rL   ÚdimÚattention_factorr&   s
             rD   r:   z5MellumRotaryEmbedding.compute_default_rope_parametersK   sÄ   € ð. Ô% jÔ1°,Ô?ˆà &Ô 6°zÔ B× FÒ FÐG^Ð`cÑ dÔ dÐÝ˜6 :¨tÑ4Ô4Ðh¸Ô8JÈfÔNhÑ8hˆÝ�(Ð2Ñ2Ñ3Ô3ˆàÐð Ø•U”\ ! S¨!µ5´;Ð?Ñ?Ô?×BÒBÈ&ÕX]ÔXcÐBÑdÔdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)rE   c                 ó|  — t          | |› d�¦  «        }t          | |› d�¦  «        }|d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬	¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd
¦  «        }	t          j        |	|	fd¬¦  «        }
|
                     ¦   «         |z  }|
                     ¦   «         |z  }d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬¦  «        |                     |j        ¬¦  «        fS )Nr-   r0   r   éÿÿÿÿr"   ÚmpsÚcpuF)Údevice_typeÚenabledrM   ©r[   rN   )rQ   rY   ÚexpandÚshaperX   rF   Ú
isinstanceÚtypeÚstrr   Ú	transposerU   ÚcatÚcosÚsinrO   )r>   ÚxÚposition_idsr,   r&   Úattention_scalingÚinv_freq_expandedÚposition_ids_expandedra   ÚfreqsÚembrk   rl   s                rD   ÚforwardzMellumRotaryEmbedding.forwardp   sâ  € õ ˜4 JÐ!9Ð!9Ð!9Ñ:Ô:ˆÝ# D¨ZÐ*KÐ*KÐ*KÑLÔLÐà$ T¨1¨1¨1¨d ]Ô3×9Ò9Ñ;Ô;×BÒBÀ<ÔCUÐVWÔCXÐZ\Ð^_Ñ`Ô`×cÒcÐdeÔdlÑmÔmÐØ ,¨Q¨Q¨Q°°a°a°a¨ZÔ 8× >Ò >Ñ @Ô @Ðå'1°!´(´-ÅÑ'EÔ'EÐkÈ!Ì(Ì-Ð[`ÒJ`ÐJ`�a”h”m�mÐfkˆÝ¨¸UÐCÑCÔCð 	0ð 	0Ø&×,Ò,Ñ.Ô.Ð1F×1LÒ1LÑ1NÔ1NÑN×YÒYÐZ[Ð]^Ñ_Ô_ˆEÝ”)˜U E˜N°Ð3Ñ3Ô3ˆCØ—'’'‘)”)Ð/Ñ/ˆCØ—'’'‘)”)Ð/Ñ/ˆCð		0ð 	0ð 	0ñ 	0ô 	0ð 	0ð 	0ð 	0ð 	0ð 	0ð 	0øøøð 	0ð 	0ð 	0ð 	0ð �vŠv˜AœGˆvÑ$Ô$ c§f¢f°1´7 fÑ&;Ô&;Ð;Ð;s   Ã-BE=Å=FÆF)NNNN©N)Ú__name__Ú
__module__Ú__qualname__rU   ÚTensorÚ__annotations__r#   r2   Ústaticmethodr   rT   rh   ÚtuplerY   r:   Úno_gradr   rt   Ú__classcell__©rC   s   @rD   r%   r%   3   s
  ø€ € € € € € ØŒlÐÐÑðU˜|ð Uð Uð Uð Uð Uð Uð* à&*Ø+/Ø"Ø!%ð	"*ð "*Ø˜tÑ#ð"*à˜Ô(ð"*ð �t‘ð"*ð ˜$‘Jð	"*ð
 
ˆ~˜uÐ$Ô	%ð"*ð "*ð "*ñ „\ð"*ðH €U„]�_„_Øð<ð <ð <ñ Ôñ „_ð<ð <ð <ð <ð <rE   r%   ÚRMSNormc                   óT   ‡ — e Zd Zd	deddfˆ fd„Zdej        dej        fd„Zd„ Zˆ xZ	S )
ÚMellumRMSNormç�íµ ÷Æ°>ÚepsrH   Nc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z<
        MellumRMSNorm is equivalent to T5LayerNorm
        N)r1   r2   r   Ú	ParameterrU   ÚonesÚweightÚvariance_epsilon)r>   rR   r„   rC   s      €rD   r2   zMellumRMSNorm.__init__…   sD   ø€ õ 	‰Œ×ÒÑÔÐÝ”l¥5¤:¨kÑ#:Ô#:Ñ;Ô;ˆŒØ #ˆÔÐÐrE   Úhidden_statesc                 ó  — |j         }|                     t          j        ¦  «        }|                     d¦  «                             dd¬¦  «        }|t          j        || j        z   ¦  «        z  }| j        |                     |¦  «        z  S )NrM   r^   T)Úkeepdim)	rO   rX   rU   Úfloat32ÚpowÚmeanÚrsqrtr‰   rˆ   )r>   rŠ   Úinput_dtypeÚvariances       rD   rt   zMellumRMSNorm.forward�   s|   € Ø#Ô)ˆØ%×(Ò(­¬Ñ7Ô7ˆØ ×$Ò$ QÑ'Ô'×,Ò,¨R¸Ð,Ñ>Ô>ˆØ%­¬°H¸tÔ?TÑ4TÑ(UÔ(UÑUˆØŒ{˜]×-Ò-¨kÑ:Ô:Ñ:Ð:rE   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)r|   rˆ   re   r‰   )r>   s    rD   Ú
extra_reprzMellumRMSNorm.extra_repr”   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIrE   )rƒ   )
rv   rw   rx   rY   r2   rU   ry   rt   r”   r~   r   s   @rD   r‚   r‚   ƒ   sŒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð JrE   r‚   c                 óœ   — | dd| j         d         dz  …f         }| d| j         d         dz  d…f         }t          j        | |fd¬¦  «        S )z*Rotates half the hidden dims of the input..Nr^   rM   rc   )re   rU   rj   )rm   Úx1Úx2s      rD   Úrotate_halfr˜   ˜   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'rE   Úrotary_pos_embc                 ó¾   — |                      |¦  «        }|                      |¦  «        }| |z  t          | ¦  «        |z  z   }||z  t          |¦  «        |z  z   }||fS )a…  Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        unsqueeze_dim (`int`, *optional*, defaults to 1):
            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
    Returns:
        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
    )Ú	unsqueezer˜   )ÚqÚkrk   rl   Úunsqueeze_dimÚq_embedÚk_embeds          rD   Úapply_rotary_pos_embr¡   Ÿ   sc   € ð& �-Š-˜Ñ
&Ô
&€CØ
�-Š-˜Ñ
&Ô
&€CØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�GÐÐrE   rŠ   Ún_reprH   c                 ó¸   — | j         \  }}}}|dk    r| S | dd…dd…ddd…dd…f                              |||||¦  «        } |                      |||z  ||¦  «        S )zÔ
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r"   N)re   rd   Úreshape)rŠ   r¢   ÚbatchÚnum_key_value_headsÚslenrL   s         rD   Ú	repeat_kvr¨   ¹   s„   € ð
 2?Ô1DÑ.€EÐ  hØ�‚z€zØÐØ! ! ! ! Q Q Q¨¨a¨a¨a°°°Ð"2Ô3×:Ò:¸5ÐBUÐW\Ð^bÐdlÑmÔm€MØ× Ò  Ð(;¸eÑ(CÀTÈ8ÑTÔTÐTrE   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutÚkwargsc                 ó  — t          || j        ¦  «        }t          || j        ¦  «        }	t          j        ||                     dd¦  «        ¦  «        |z  }
|�|
|z   }
t
          j                             |
dt          j        ¬¦  «         	                    |j
        ¦  «        }
t
          j                             |
|| j        ¬¦  «        }
t          j        |
|	¦  «        }|                     dd¦  «                             ¦   «         }||
fS )NrM   r   r^   )r[   rO   )ÚpÚtrainingr"   )r¨   Únum_key_value_groupsrU   Úmatmulri   r   Ú
functionalÚsoftmaxr�   rX   rO   r°   r´   Ú
contiguous)rª   r«   r¬   r­   r®   r¯   r°   r±   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               rD   Úeager_attention_forwardr¾   Å   sé   € õ ˜3 Ô ;Ñ<Ô<€JÝ˜U FÔ$?Ñ@Ô@€Lå”<  z×';Ò';¸A¸qÑ'AÔ'AÑBÔBÀWÑL€LØÐ!Ø# nÑ4ˆå”=×(Ò(¨¸2ÅUÄ]Ð(ÑSÔS×VÒVÐW\ÔWbÑcÔc€LÝ”=×(Ò(¨¸È6Ì?Ð(Ñ[Ô[€LÝ”,˜|¨\Ñ:Ô:€KØ×'Ò'¨¨1Ñ-Ô-×8Ò8Ñ:Ô:€Kà˜Ð$Ð$rE   c                   óÊ   ‡ — e Zd ZdZdedefˆ fd„Z	 ddej        de	ej        ej        f         dej        dz  d	e
dz  d
ee         de	ej        ej        dz  f         fd„Zˆ xZS )ÚMellumAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr'   Ú	layer_idxc                 ól  •— t          ¦   «                              ¦   «          || _        || _        t	          |d|j        |j        z  ¦  «        | _        |j        |j        z  | _	        | j        dz  | _
        |j        | _        d| _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        | j        z  |j        |j        ¬¦  «        | _        t)          | j        |j        ¬¦  «        | _        t)          | j        |j        ¬¦  «        | _        |j        |         dk    r|j        nd | _        d S )NrL   g      à¿T©Úbias©r„   Úsliding_attention)r1   r2   r'   rÁ   rQ   rR   rS   rL   r¦   rµ   r¯   Úattention_dropoutÚ	is_causalr   ÚLinearÚattention_biasÚq_projÚk_projÚv_projÚo_projr‚   Úrms_norm_epsÚq_normÚk_normr8   Úsliding_window©r>   r'   rÁ   rC   s      €rD   r2   zMellumAttention.__init__â   sœ  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒå”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ&¨¬Ñ6¸Ô8JÐQWÔQfð
ñ 
ô 
ˆŒõ $ D¤M°vÔ7JÐKÑKÔKˆŒÝ# D¤M°vÔ7JÐKÑKÔKˆŒØ7=Ô7IÈ)Ô7TÐXkÒ7kÐ7k˜fÔ3Ð3ÐquˆÔÐÐrE   NrŠ   Úposition_embeddingsr®   Úpast_key_valuesr±   rH   c                 óz  — |j         d d…         }g |¢d‘| j        ‘R }|                      |                      |¦  «                             |¦  «        ¦  «                             dd¦  «        }|                      |                      |¦  «                             |¦  «        ¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�| 
                    |	|
| j        ¦  «        \  }	}
t          j        | j        j        t           ¦  «        } || ||	|
|f| j        sdn| j        | j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )Nr^   r"   rM   r©   )r°   r¯   rÒ   )re   rL   rÐ   rË   Úviewri   rÑ   rÌ   rÍ   r¡   ÚupdaterÁ   r   Úget_interfacer'   Ú_attn_implementationr¾   r´   rÇ   r¯   rÒ   r¤   r¹   rÎ   )r>   rŠ   rÔ   r®   rÕ   r±   Úinput_shapeÚhidden_shapeÚquery_statesrº   r»   rk   rl   Úattention_interfacer½   r¼   s                   rD   rt   zMellumAttention.forwardü   sà  € ð $Ô)¨#¨2¨#Ô.ˆØ8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆà—{’{ 4§;¢;¨}Ñ#=Ô#=×#BÒ#BÀ<Ñ#PÔ#PÑQÔQ×[Ò[Ð\]Ð_`ÑaÔaˆØ—[’[ §¢¨]Ñ!;Ô!;×!@Ò!@ÀÑ!NÔ!NÑOÔO×YÒYÐZ[Ð]^Ñ_Ô_ˆ
Ø—{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆà&‰ˆˆSÝ#7¸ÀjÐRUÐWZÑ#[Ô#[Ñ ˆ�jàÐ&Ø'6×'=Ò'=¸jÈ,ÐX\ÔXfÑ'gÔ'gÑ$ˆJ˜å(?Ô(MØŒKÔ,Õ.Eñ)
ô )
Ðð %8Ð$7ØØØØØð
%
ð  $œ}ÐH�C�C°$Ô2HØ”LØÔ.ð
%
ð 
%
ð ð
%
ð 
%
Ñ!ˆ�\ð *�kÔ)Ð;¨;Ð;¸Ð;Ð;Ð;×FÒFÑHÔHˆØ—k’k +Ñ.Ô.ˆØ˜LÐ(Ð(rE   ru   )rv   rw   rx   Ú__doc__r#   rT   r2   rU   ry   r|   r	   r   r   rt   r~   r   s   @rD   rÀ   rÀ   Þ   så   ø€ € € € € àGÐGðv˜|ð v¸ð vð vð vð vð vð vð> )-ð')ð ')à”|ð')ð # 5¤<°´Ð#=Ô>ð')ð œ tÑ+ð	')ð
  ™ð')ð Ð-Ô.ð')ð 
ˆuŒ|˜Uœ\¨DÑ0Ð0Ô	1ð')ð ')ð ')ð ')ð ')ð ')ð ')ð ')rE   rÀ   c                   ób   ‡ — e Zd ZdZˆ fd„Zdej        dej        dej        dej        fd„Zˆ xZS )ÚMellumExpertsz2Collection of expert weights stored as 3D tensors.c                 ó´  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        |j        | _        t          j        t          j
        | j        d| j        z  | j        ¦  «        ¦  «        | _        t          j        t          j
        | j        | j        | j        ¦  «        ¦  «        | _        t          |j                 | _        d S )NrM   )r1   r2   Únum_expertsrR   Ú
hidden_dimÚmoe_intermediate_sizeÚintermediate_dimr   r†   rU   ÚemptyÚgate_up_projÚ	down_projr   Ú
hidden_actÚact_fn©r>   r'   rC   s     €rD   r2   zMellumExperts.__init__*  s£   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔØ Ô,ˆŒØ &Ô <ˆÔÝœL­¬°TÔ5EÀqÈ4ÔK`ÑG`ÐbfÔbqÑ)rÔ)rÑsÔsˆÔÝœ¥e¤k°$Ô2BÀDÄOÐUYÔUjÑ&kÔ&kÑlÔlˆŒÝ˜VÔ.Ô/ˆŒˆˆrE   rŠ   Útop_k_indexÚtop_k_weightsrH   c                 ó€  — t          j        |¦  «        }t          j        ¦   «         5  t           j        j                             || j        ¬¦  «        }|                     ddd¦  «        }t          j        | 	                    d¬¦  «        d¦  «         
                    ¦   «         }d d d ¦  «         n# 1 swxY w Y   |D ]þ}|d         }|| j        k    rŒt          j        ||         ¦  «        \  }}	||	         }
t          j                             |
| j        |         ¦  «                             dd¬¦  «        \  }}|                      |¦  «        |z  }t          j                             || j        |         ¦  «        }|||	|d f         z  }|                     d|	|                     |j        ¦  «        ¦  «         Œÿ|S )N)Únum_classesrM   r"   r   )r^   éþÿÿÿrc   r^   )rU   Ú
zeros_liker}   r   r·   Úone_hotrã   ÚpermuteÚgreaterÚsumÚnonzeroÚwhereÚlinearrè   Úchunkrë   ré   Ú
index_add_rX   rO   )r>   rŠ   rí   rî   Úfinal_hidden_statesÚexpert_maskÚ
expert_hitÚ
expert_idxÚ	top_k_posÚ	token_idxÚcurrent_stateÚgateÚupÚcurrent_hidden_statess                 rD   rt   zMellumExperts.forward3  sø  € õ $Ô.¨}Ñ=Ô=ÐÝŒ]‰_Œ_ð 	Sð 	SÝœ(Ô-×5Ò5°kÈtÔO_Ð5Ñ`Ô`ˆKØ%×-Ò-¨a°°AÑ6Ô6ˆKÝœ {§¢¸8 Ñ'DÔ'DÀaÑHÔH×PÒPÑRÔRˆJð	Sð 	Sð 	Sñ 	Sô 	Sð 	Sð 	Sð 	Sð 	Sð 	Sð 	Søøøð 	Sð 	Sð 	Sð 	Sð
 %ð 
	nð 
	nˆJØ# AœˆJØ˜TÔ-Ò-Ð-ØÝ#(¤;¨{¸:Ô/FÑ#GÔ#GÑ ˆI�yØ)¨)Ô4ˆMÝ”}×+Ò+¨M¸4Ô;LÈZÔ;XÑYÔY×_Ò_Ð`aÐgiÐ_ÑjÔj‰HˆD�"Ø$(§K¢K°Ñ$5Ô$5¸Ñ$:Ð!Ý$&¤M×$8Ò$8Ð9NÐPTÔP^Ð_iÔPjÑ$kÔ$kÐ!Ø$9¸MÈ)ÐU^Ð`dÐJdÔ<eÑ$eÐ!Ø×*Ò*¨1¨iÐ9N×9QÒ9QÐReÔRkÑ9lÔ9lÑmÔmÐmÐmà"Ð"s   ¨A>B2Â2B6Â9B6)	rv   rw   rx   rß   r2   rU   ry   rt   r~   r   s   @rD   rá   rá   &  s€   ø€ € € € € à<Ð<ð0ð 0ð 0ð 0ð 0ð#à”|ð#ð ”\ð#ð ”|ð	#ð
 
Œð#ð #ð #ð #ð #ð #ð #ð #rE   rá   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚMellumTopKRouterc                 ó  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        |j        | _        |j        | _        t          j	        t          j        | j        | j        ¦  «        ¦  «        | _        d S ru   )r1   r2   Únum_experts_per_tokÚtop_krã   Únorm_topk_probrR   rä   r   r†   rU   Úzerosrˆ   rì   s     €rD   r2   zMellumTopKRouter.__init__O  si   ø€ Ý‰Œ×ÒÑÔÐØÔ/ˆŒ
Ø!Ô-ˆÔØ$Ô3ˆÔØ Ô,ˆŒÝ”l¥5¤;¨tÔ/?ÀÄÑ#QÔ#QÑRÔRˆŒˆˆrE   c                 ó�  — |                      d| j        ¦  «        }t          j        || j        ¦  «        }t
          j        j                             |t
          j	        d¬¦  «        }t          j
        || j        d¬¦  «        \  }}| j        r||                     dd¬¦  «        z  }|                     |j        ¦  «        }|}|||fS )Nr^   )rO   r[   rc   T)r[   rŒ   )r¤   rä   ÚFrù   rˆ   rU   r   r·   r¸   rY   Útopkr
  r  rö   rX   rO   )r>   rŠ   Úrouter_logitsÚrouter_probsÚrouter_top_valueÚrouter_indicesÚrouter_scoress          rD   rt   zMellumTopKRouter.forwardW  sÁ   € Ø%×-Ò-¨b°$´/ÑBÔBˆÝœ °´Ñ<Ô<ˆÝ”xÔ*×2Ò2°=ÍÌÐY[Ð2Ñ\Ô\ˆÝ+0¬:°lÀDÄJÐTVÐ+WÑ+WÔ+WÑ(Ð˜.ØÔð 	KØÐ 0× 4Ò 4¸ÀTÐ 4Ñ JÔ JÑJÐØ+×.Ò.¨}Ô/BÑCÔCÐØ(ˆØ˜m¨^Ð;Ð;rE   ©rv   rw   rx   r2   rt   r~   r   s   @rD   r  r  N  sL   ø€ € € € € ðSð Sð Sð Sð Sð	<ð 	<ð 	<ð 	<ð 	<ð 	<ð 	<rE   r  c                   óH   ‡ — e Zd Zdefˆ fd„Zdej        dej        fd„Zˆ xZS )ÚMellumSparseMoeBlockr'   c                 ó˜   •— t          ¦   «                              ¦   «          t          |¦  «        | _        t	          |¦  «        | _        d S ru   )r1   r2   rá   Úexpertsr  r  rì   s     €rD   r2   zMellumSparseMoeBlock.__init__d  s;   ø€ Ý‰Œ×ÒÑÔÐÝ$ VÑ,Ô,ˆŒÝ$ VÑ,Ô,ˆŒ	ˆ	ˆ	rE   rŠ   rH   c                 óÒ   — |j         \  }}}|                     d|¦  «        }|                      |¦  «        \  }}}|                      |||¦  «        }	|	                     |||¦  «        S )Nr^   )re   r×   r  r  r¤   )
r>   rŠ   Ú
batch_sizeÚsequence_lengthrä   Úhidden_states_reshapedÚ_Úrouting_weightsÚselected_expertsrü   s
             rD   rt   zMellumSparseMoeBlock.forwardi  sr   € Ø2?Ô2EÑ/ˆ
�O ZØ!.×!3Ò!3°B¸
Ñ!CÔ!CÐØ/3¯yªyÐ9OÑ/PÔ/PÑ,ˆˆ?Ð,Ø"ŸlšlÐ+AÐCSÐUdÑeÔeÐØ"×*Ò*¨:°È
ÑSÔSÐSrE   )	rv   rw   rx   r#   r2   rU   ry   rt   r~   r   s   @rD   r  r  c  st   ø€ € € € € ð-˜|ð -ð -ð -ð -ð -ð -ð
T U¤\ð T°e´lð Tð Tð Tð Tð Tð Tð Tð TrE   r  c                   ó&   ‡ — e Zd Zdˆ fd„	Zd„ Zˆ xZS )Ú	MellumMLPNc                 ó   •— t          ¦   «                              ¦   «          || _        |j        | _        |€|j        n|| _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        d S ©NFrÃ   )r1   r2   r'   rR   Úintermediate_sizer   rÉ   Ú	gate_projÚup_projré   r   rê   rë   )r>   r'   r%  rC   s      €rD   r2   zMellumMLP.__init__r  s±   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ!Ô-ˆÔØ=NÐ=V Ô!9Ð!9Ð\mˆÔÝœ 4Ô#3°TÔ5KÐRWÐXÑXÔXˆŒÝ”y Ô!1°4Ô3IÐPUÐVÑVÔVˆŒÝœ 4Ô#9¸4Ô;KÐRWÐXÑXÔXˆŒÝ˜VÔ.Ô/ˆŒˆˆrE   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S ru   )ré   rë   r&  r'  )r>   rm   ré   s      rD   rt   zMellumMLP.forward|  sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐrE   ru   r  r   s   @rD   r"  r"  q  sL   ø€ € € € € ð0ð 0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð rE   r"  c                   óÒ   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 	 ddej        dej        dz  dej        dz  d	e	dz  d
e
dz  deej        ej        f         dz  dee         dej        fd„Zˆ xZS )ÚMellumDecoderLayerr'   rÁ   c                 óŒ  •— t          ¦   «                              ¦   «          |j        | _        t          ||¦  «        | _        |j        |         dk    rt          |¦  «        | _        nt          ||j	        ¬¦  «        | _        t          |j        |j        ¬¦  «        | _        t          |j        |j        ¬¦  «        | _        d S )NÚsparse)r%  rÅ   )r1   r2   rR   rÀ   Ú	self_attnÚmlp_layer_typesr  Úmlpr"  r%  r‚   rÏ   Úinput_layernormÚpost_attention_layernormrÓ   s      €rD   r2   zMellumDecoderLayer.__init__‚  s¬   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔÝ(¨°Ñ;Ô;ˆŒØÔ! )Ô,°Ò8Ð8Ý+¨FÑ3Ô3ˆDŒHˆHå  ¸6Ô;SÐTÑTÔTˆDŒHÝ,¨VÔ-?ÀVÔEXÐYÑYÔYˆÔÝ(5°fÔ6HÈfÔNaÐ(bÑ(bÔ(bˆÔ%Ð%Ð%rE   NFrŠ   r®   rn   rÕ   Ú	use_cacherÔ   r±   rH   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)rŠ   r®   rn   rÕ   r2  rÔ   © )r0  r-  r1  r/  )
r>   rŠ   r®   rn   rÕ   r2  rÔ   r±   Úresidualr  s
             rD   rt   zMellumDecoderLayer.forward�  s¡   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆà)˜4œ>ð 
Ø'Ø)Ø%Ø+ØØ 3ð
ð 
ð ð
ð 
Ñˆ�qð ! =Ñ0ˆð !ˆØ×5Ò5°mÑDÔDˆØŸš Ñ/Ô/ˆØ  =Ñ0ˆØÐrE   )NNNFN)rv   rw   rx   r#   rT   r2   rU   ry   Ú
LongTensorr	   Úboolr|   r   r   rt   r~   r   s   @rD   r*  r*  �  sÿ   ø€ € € € € ð	c˜|ð 	c¸ð 	cð 	cð 	cð 	cð 	cð 	cð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð rE   r*  c                   óž   ‡ — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZ eed¬¦  «        eedœZ ej        ¦   «         ˆ fd	„¦   «         Zˆ xZS )
ÚMellumPreTrainedModelr'   ÚmodelTr*  rÕ   r   )Úindex)r  rŠ   Ú
attentionsc                 óÄ  •— t          ¦   «                              |¦  «         | j        j        }t	          |t
          ¦  «        r9t          j        |j        d|¬¦  «         t          j        |j	        d|¬¦  «         n1t	          |t          ¦  «        rt          j        |j        d|¬¦  «         t	          |t          ¦  «        r›|j        D ]•}|j        }|j        |         dk    rt           |j        |                  } ||j        |¬¦  «        \  }}t          j        t%          ||› d�¦  «        |¦  «         t          j        t%          ||› d�¦  «        |¦  «         Œ”d S d S )Nr©   )r�   Ústdr*   r+   r-   r/   )r1   Ú_init_weightsr'   Úinitializer_rangerf   rá   ÚinitÚnormal_rè   ré   r  rˆ   r%   r8   r:   r)   r   Úcopy_rQ   )r>   rª   r>  r,   r@   rA   r  rC   s          €rD   r?  z#MellumPreTrainedModel._init_weightsÀ  so  ø€ å‰Œ×Ò˜fÑ%Ô%Ð%ØŒkÔ+ˆÝ�f�mÑ,Ô,ð 	;ÝŒL˜Ô,°3¸CÐ@Ñ@Ô@Ð@ÝŒL˜Ô)°¸Ð=Ñ=Ô=Ð=Ð=Ý˜Õ 0Ñ1Ô1ð 	;ÝŒL˜œ¨S°cÐ:Ñ:Ô:Ð:Ý�fÕ3Ñ4Ô4ð 	^Ø$Ô0ð ^ð ^�
Ø%ÔE�ØÔ# JÔ/°9Ò<Ð<Ý#6°vÔ7GÈ
Ô7SÔ#T�LØ#/ <°´È*Ð#UÑ#UÔ#UÑ �˜qÝ”
�7 6¨jÐ+CÐ+CÐ+CÑDÔDÀmÑTÔTÐTÝ”
�7 6¨jÐ+LÐ+LÐ+LÑMÔMÈ}Ñ]Ô]Ð]Ð]ð	^ð 	^ð^ð ^rE   )rv   rw   rx   r#   rz   Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendr    r  r*  rÀ   Ú_can_record_outputsrU   r}   r?  r~   r   s   @rD   r9  r9  ­  sÄ   ø€ € € € € € àÐÐÑØÐØ&*Ð#Ø-Ð.ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà'˜Ð(8ÀÐBÑBÔBØ+Ø%ðð Ðð €U„]�_„_ð^ð ^ð ^ð ^ñ „_ð^ð ^ð ^ð ^ð ^rE   r9  c                   óâ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 	 	 ddej	        dz  dej
        dz  dej	        dz  dedz  dej        dz  d	edz  d
ee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚMellumModelr'   c                 óÞ  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS r4  )r*  )Ú.0rÁ   r'   s     €rD   ú
<listcomp>z(MellumModel.__init__.<locals>.<listcomp>Ü  s$   ø€ ÐdÐdÐd°yÕ ¨	Ñ2Ô2ÐdÐdÐdrE   rÅ   ©r'   F)r1   r2   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	EmbeddingrR   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr‚   rÏ   Únormr%   Ú
rotary_embÚgradient_checkpointingÚ	post_initrì   s    `€rD   r2   zMellumModel.__init__Õ  sÔ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØdÐdÐdÐdÅEÈ&ÔJbÑDcÔDcÐdÑdÔdñ
ô 
ˆŒõ " &Ô"4¸&Ô:MÐNÑNÔNˆŒ	Ý/°vÐ>Ñ>Ô>ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐrE   NÚ	input_idsr®   rn   rÕ   Úinputs_embedsr2  r±   rH   c           	      ó˜  ‡— |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          |x}	t          ¦  «        sI| j        ||||dœŠˆfd„ˆfd„d	œ}
i }	t          | j        j        ¦  «        D ]} |
|         ¦   «         |	|<   Œ|}i }t          | j        j        ¦  «        D ]}|                      |||¦  «        ||<   Œt          | j        d | j        j        …         ¦  «        D ]?\  }} ||f|	| j        j        |                  || j        j        |                  ||d
œ|¤Ž}Œ@|                      |¦  «        }t'          ||r|nd ¬¦  «        S )Nz:You must specify exactly one of input_ids or inputs_embedsrT  r   r"   )rF   )r'   rc  r®   rÕ   rn   c                  ó   •— t          di ‰ ¤ŽS ©Nr4  )r   ©Úmask_kwargss   €rD   ú<lambda>z%MellumModel.forward.<locals>.<lambda>	  s   ø€ Õ*<Ð*KÐ*K¸{Ð*KÐ*K€ rE   c                  ó   •— t          di ‰ ¤ŽS rf  )r   rg  s   €rD   ri  z%MellumModel.forward.<locals>.<lambda>
  s   ø€ Õ-NÐ-]Ð-]ÐQ\Ð-]Ð-]€ rE   )Úfull_attentionrÆ   )r®   rÔ   rn   rÕ   )Úlast_hidden_staterÕ   )Ú
ValueErrorrY  r
   r'   Úget_seq_lengthrU   rV   re   rF   r›   rf   Údictr7   r8   r_  Ú	enumerater]  r\  r^  r   )r>   rb  r®   rn   rÕ   rc  r2  r±   Úpast_seen_tokensÚcausal_mask_mappingÚmask_creation_functionsr,   rŠ   rÔ   ÚiÚdecoder_layerrh  s                   @rD   rt   zMellumModel.forwardå  sc  ø€ ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø ×-Ò-¨iÑ8Ô8ˆMàð 	?˜Ð0Ý*°$´+Ð>Ñ>Ô>ˆOàÐØCRÐC^˜×=Ò=Ñ?Ô?Ð?ÐdeÐÝ œ<¨Ô(;¸AÔ(>À}ÔG[Ð\Ñ\Ô\Ð_oÑoˆLØ'×1Ò1°!Ñ4Ô4ˆLå°Ð?Ð-ÅÑFÔFð 	Xàœ+Ø!.Ø"0Ø#2Ø ,ðð ˆKð #LÐ"KÐ"KÐ"KØ%]Ð%]Ð%]Ð%]ð'ð 'Ð#ð #%ÐÝ! $¤+Ô"9Ñ:Ô:ð Xð X�
Ø2UÐ2IÈ*Ô2UÑ2WÔ2WÐ# JÑ/Ð/à%ˆØ ÐÝ˜dœkÔ5Ñ6Ô6ð 	gð 	gˆJØ.2¯oªo¸mÈ\Ð[eÑ.fÔ.fÐ 
Ñ+Ð+å )¨$¬+Ð6U¸¼Ô8UÐ6UÔ*VÑ WÔ Wð 	ð 	ÑˆAˆ}Ø)˜MØðà2°4´;Ô3JÈ1Ô3MÔNØ$7¸¼Ô8OÐPQÔ8RÔ$SØ)Ø /ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆå%Ø+Ø/8ÐB˜O˜O¸dð
ñ 
ô 
ð 	
rE   )NNNNNN)rv   rw   rx   r#   r2   r   r!   r   rU   r6  ry   r	   ÚFloatTensorr7  r   r   r   rt   r~   r   s   @rD   rO  rO  Ó  s  ø€ € € € € ð˜|ð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð<
ð <
àÔ# dÑ*ð<
ð œ tÑ+ð<
ð Ô&¨Ñ-ð	<
ð
  ™ð<
ð Ô(¨4Ñ/ð<
ð ˜$‘;ð<
ð Ð+Ô,ð<
ð 
 ð<
ð <
ð <
ñ „^ñ „_ñ  Ôð<
ð <
ð <
ð <
ð <
rE   rO  rM   Úgate_logitsrã   c                 óÆ  ‡— | �t          | t          ¦  «        sdS t          | t          ¦  «        r/| d         j        Št          j        ˆfd„| D ¦   «         d¬¦  «        }t          j        j                             |d¬¦  «        }t          j        ||d¬¦  «        \  }}t          j        j         	                    ||¦  «        }|€@t          j
        |                     ¦   «         d¬¦  «        }	t          j
        |d¬¦  «        }
�n.|j        \  }}|j        d         ||z  z  }|ddd…dd…ddf                              |||||f¦  «                             d||¦  «                             ‰¦  «        }t          j        |                     ¦   «         |z  d¬¦  «        t          j        |d¬¦  «        z  }	|ddd…dd…df                              ||||f¦  «                             d|¦  «                             ‰¦  «        }t          j        ||z  d¬¦  «        t          j        |d¬¦  «        z  }
t          j        |	|
                     d¦  «        z  ¦  «        }||z  S )aÄ  
    Computes auxiliary load balancing loss as in Switch Transformer - implemented in Pytorch.

    See Switch Transformer (https://huggingface.co/papers/2101.03961) for more details. This function implements the loss
    function presented in equations (4) - (6) of the paper. It aims at penalizing cases where the routing between
    experts is too unbalanced.

    Args:
        gate_logits:
            Logits from the `gate`, should be a tuple of model.config.num_hidden_layers tensors of
            shape [batch_size X sequence_length, num_experts].
        num_experts:
            Number of experts
        top_k:
            The number of experts to route per-token, can be also interpreted as the `top-k` routing
            parameter.
        attention_mask (`torch.Tensor`, *optional*):
            The attention_mask used in forward function
            shape [batch_size X sequence_length] if not None.

    Returns:
        The auxiliary loss.
    Nr   c                 ó:   •— g | ]}|                      ‰¦  «        ‘ŒS r4  )rX   )rR  Ú
layer_gateÚcompute_devices     €rD   rS  z,load_balancing_loss_func.<locals>.<listcomp>I  s&   ø€ Ð-jÐ-jÐ-jÐPZ¨j¯mªm¸NÑ.KÔ.KÐ-jÐ-jÐ-jrE   rc   r^   )rf   r|   rF   rU   rj   r   r·   r¸   r  ró   r�   rY   re   rd   r¤   rX   rö   r›   )rw  rã   r
  r®   Úconcatenated_gate_logitsr  r  r   rý   Útokens_per_expertÚrouter_prob_per_expertr  r  r\  Úexpert_attention_maskÚ router_per_expert_attention_maskÚoverall_lossr{  s                    @rD   Úload_balancing_loss_funcr‚  '  s�  ø€ ð: Ð¥*¨[½%Ñ"@Ô"@ÐØˆqå�+�uÑ%Ô%ð sØ$ QœÔ.ˆÝ#(¤9Ð-jÐ-jÐ-jÐ-jÐ^iÐ-jÑ-jÔ-jÐpqÐ#rÑ#rÔ#rÐ å”hÔ)×1Ò1Ð2JÐPRÐ1ÑSÔS€Oåœ* _°eÀÐDÑDÔDÑ€AÐå”(Ô%×-Ò-Ð.>ÀÑLÔL€KàÐå!œJ {×'8Ò'8Ñ':Ô':ÀÐBÑBÔBÐõ "'¤¨OÀÐ!CÑ!CÔ!CÐÑà&4Ô&:Ñ#ˆ
�OØ4Ô:¸1Ô=À*ÈÑB^Ñ_Ðð ˜4    A A A t¨TÐ1Ô2ßŠVÐ&¨
°OÀUÈKÐXÑYÔYßŠW�R˜ Ñ,Ô,ßŠR�ÑÔð	 	õ "œI k×&7Ò&7Ñ&9Ô&9Ð<QÑ&QÐWXÐYÑYÔYÕ\aÔ\eØ! qð]
ñ ]
ô ]
ñ 
Ðð ˜4    A A A tÐ+Ô,ßŠVÐ&¨
°OÀ[ÐQÑRÔRßŠW�R˜Ñ%Ô%ßŠR�ÑÔð	 	)õ "'¤¨?Ð=]Ñ+]ÐcdÐ!eÑ!eÔ!eÕhmÔhqØ,°!ði
ñ i
ô i
ñ "
Ðõ ”9Ð.Ð1G×1QÒ1QÐRSÑ1TÔ1TÑTÑUÔU€LØ˜+Ñ%Ð%rE   c                   ó$  ‡ — e Zd ZddiZddiZddgdgfiZˆ fd„Zee	 	 	 	 	 	 	 	 	 dd
e	j
        dz  de	j        dz  de	j
        dz  dedz  de	j        dz  de	j
        dz  dedz  dedz  dee	j        z  dee         defd„¦   «         ¦   «         Zˆ xZS )ÚMellumForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputrŠ   Úlogitsc                 óF  •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |j	        | _	        |j
        | _
        |j        | _        |                      ¦   «          d S r$  )r1   r2   rO  r:  rW  r   rÉ   rR   r…  Úrouter_aux_loss_coefrã   r	  ra  rì   s     €rD   r2   zMellumForCausalLM.__init__  s‹   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý  Ñ(Ô(ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒØ$*Ô$?ˆÔ!Ø!Ô-ˆÔØ#)Ô#=ˆÔ ð 	�ŠÑÔÐÐÐrE   Nr   rb  r®   rn   rÕ   rc  Úlabelsr2  Úoutput_router_logitsÚlogits_to_keepr±   rH   c
                 ó  — |�|n| j         j        } | j        d|||||||dœ|
¤Ž}|j        }t	          |	t
          ¦  «        rt          |	 d¦  «        n|	}|                      |dd…|dd…f         ¦  «        }d}|� | j        ||| j	        fi |
¤Ž}d}|rHt          |j        | j        | j        |¦  «        }|�%|| j        |                     |j        ¦  «        z  z  }t#          ||||j        |j        |j        |j        ¬¦  «        S )ar  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Example:

        ```python
        >>> from transformers import AutoTokenizer, MellumForCausalLM

        >>> model = MellumForCausalLM.from_pretrained("Qwen/Qwen3-MoE-15B-A2B")
        >>> tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-MoE-15B-A2B")

        >>> prompt = "Hey, are you conscious? Can you talk to me?"
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```N)rb  r®   rn   rÕ   rc  r2  r‹  )ÚlossÚaux_lossr‡  rÕ   rŠ   r<  r  r4  )r'   r‹  r:  rl  rf   rT   Úslicer…  Úloss_functionrW  r‚  r  rã   r	  r‰  rX   rF   r   rÕ   rŠ   r<  )r>   rb  r®   rn   rÕ   rc  rŠ  r2  r‹  rŒ  r±   ÚoutputsrŠ   Úslice_indicesr‡  rŽ  r�  s                    rD   rt   zMellumForCausalLM.forward‹  sn  € ðN %9Ð$DÐ Ð È$Ì+ÔJjð 	ð
 +5¨$¬*ð 	+
ØØ)Ø%Ø+Ø'ØØ!5ð	+
ð 	+
ð ð	+
ð 	+
ˆð  Ô1ˆå8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆàˆØÐØ%�4Ô% f¨f°d´oÐPÐPÈÐPÐPˆDàˆØð 	MÝ/ØÔ%ØÔ ØÔ(Øñ	ô ˆHð Ð!Ø˜Ô1°H·K²KÀÄÑ4LÔ4LÑLÑL�å(ØØØØ#Ô3Ø!Ô/ØÔ)Ø!Ô/ð
ñ 
ô 
ð 	
rE   )	NNNNNNNNr   )rv   rw   rx   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr2   r   r   rU   r6  ry   r	   rv  r7  rT   r   r   r   rt   r~   r   s   @rD   r„  r„  y  sp  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hð
ð 
ð 
ð 
ð 
ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø,0Ø-.ðP
ð P
àÔ# dÑ*ðP
ð œ tÑ+ðP
ð Ô&¨Ñ-ð	P
ð
  ™ðP
ð Ô(¨4Ñ/ðP
ð Ô  4Ñ'ðP
ð ˜$‘;ðP
ð # T™kðP
ð ˜eœlÑ*ðP
ð Ð+Ô,ðP
ð 
#ðP
ð P
ð P
ñ „^ñ ÔðP
ð P
ð P
ð P
ð P
rE   r„  )r„  rO  r9  )r"   )r©   )NrM   N)LÚcollections.abcr   Útypingr   rU   Útorch.nn.functionalr   r·   r  Ú r   rA  Úactivationsr   Úcache_utilsr	   r
   Ú
generationr   Úintegrationsr   r   r   r   Úmasking_utilsr   r   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   Úutils.genericr   r   r   Úutils.output_capturingr    r!   Úconfiguration_mellumr#   ÚModuler%   r‚   r˜   r¡   ry   rT   r¨   rY   r¾   rÀ   rá   r  r  r"  r*  r9  rO  r|   r‚  r„  Ú__all__r4  rE   rD   ú<module>r¬     sÞ  ðð* %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð Ð Ð Ð Ø Ð Ð Ð Ð Ð à &Ð &Ð &Ð &Ð &Ð &Ø !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )ðð ð ð ð ð ð ð ð ð ð ð ð SÐ RÐ RÐ RÐ RÐ RÐ RÐ RØ BÐ BÐ BÐ BÐ BÐ BØ 9Ð 9Ð 9Ð 9Ð 9Ð 9Ø QÐ QÐ QÐ QÐ QÐ QÐ QÐ QØ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KØ FÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø 5Ð 5Ð 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø [Ð [Ð [Ð [Ð [Ð [Ð [Ð [Ð [Ð [Ø EÐ EÐ EÐ EÐ EÐ EÐ EÐ EØ .Ð .Ð .Ð .Ð .Ð .ðM<ð M<ð M<ð M<ð M<˜BœIñ M<ô M<ð M<ð` Ð˜YÑ'Ô'ðJð Jð Jð Jð J�B”Iñ Jô Jñ (Ô'ðJð((ð (ð (ð ÐÐ*Ñ+Ô+ðð ð ñ ,Ô+ðð2	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð2 ÐÐ)Ñ*Ô*ðD)ð D)ð D)ð D)ð D)�b”iñ D)ô D)ñ +Ô*ðD)ðN ð$#ð $#ð $#ð $#ð $#�B”Iñ $#ô $#ñ Ôð$#ðN<ð <ð <ð <ð <�r”yñ <ô <ð <ð*Tð Tð Tð Tð T˜2œ9ñ Tô Tð Tðð ð ð ð �”	ñ ô ð ð )ð )ð )ð )ð )Ð3ñ )ô )ð )ðX ð"^ð "^ð "^ð "^ð "^˜Oñ "^ô "^ñ „ð"^ðJ ðP
ð P
ð P
ð P
ð P
Ð'ñ P
ô P
ñ „ðP
ðj #Ø
Ø*.ð	O&ð O&Ø”  e¤lÔ 3Ñ3°dÑ:ðO&à�t‘ðO&ð ”L 4Ñ'ð	O&ð
 „\�CÑðO&ð O&ð O&ð O&ðd ðc
ð c
ð c
ð c
ð c
Ð-¨ñ c
ô c
ñ „ðc
ðL HÐ
GÐ
G€€€rE   